Prepositional Phrase Attachment over Word Embedding Products
نویسندگان
چکیده
We present a low-rank multi-linear model for the task of solving prepositional phrase attachment ambiguity (PP task). Our model exploits tensor products of word embeddings, capturing all possible conjunctions of latent embeddings. Our results on a wide range of datasets and task settings show that tensor products are the best compositional operation and that a relatively simple multi-linear model that uses only word embeddings of lexical features can outperform more complex non-linear architectures that exploit the same information. Our proposed model gives the current best reported performance on an out-of-domain evaluation and performs competively on out-of-domain dependency parsing datasets.
منابع مشابه
Disambiguating prepositional phrase attachment sites with sense information captured in contextualized distributional data
This work presents a supervised prepositional phrase (PP) attachment disambiguation system that uses contextualized distributional information as the distance metric for a nearest-neighbor classifier. Contextualized word vectors constructed from the GigaWord Corpus provide a method for implicit Word Sense Disambiguation (WSD), whose reliability helps this system outperform baselines and achieve...
متن کاملExploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment
Prepositional phrase (PP) attachment disambiguation is a known challenge in syntactic parsing. The lexical sparsity associated with PP attachments motivates research in word representations that can capture pertinent syntactic and semantic features of the word. One promising solution is to use word vectors induced from large amounts of raw text. However, state-of-the-art systems that employ suc...
متن کاملL2 Learners’ English Prepositional-Phrase Processing with Consideration of L2 Proficiency and Word Familiarity: A mixed-effect Analysis
A considerable number of studies have hitherto examined how native speakers and second language (hereafter L1 and L2, respectively) learners of English process English prepositional phrases. It is usually thought that both L1 and L2 speakers have a preference for verb phrase modification (e.g., The boy broke the old window with a ball of snow.) over noun phrase modification (e.g., The boy broke...
متن کاملEnsemble Learning for Low Resources Prepositional Phrase Attachment
Prepositional phrase attachment is a major disambiguation problem when it’s about parsing natural language, for many languages. In this paper a low resources policy is proposed using supervised machine learning algorithms in order to resolve the disambiguation problem of prepositional phrase attachment in Modern Greek. It is a first attempt to resolve prepositional phrase attachment in Modern G...
متن کاملNeural Network Architectures for Prepositional Phrase Attachment Disambiguation
This thesis addresses the problem of Prepositional Phrase (PP) attachment disambiguation, a key challenge in syntactic parsing. In natural language sentences, a PP may often be attached to several possible candidates. While humans can usually identify the correct candidate successfully, syntactic parsers are known to have high error rated on this kind of construction. This work explores the use...
متن کامل